La recerca s'articula en dues línies amb els objectius que es detallen a continuació.

Percepció i Manipulació:
1. Enllaçar percepció i acció utilitzant mètodes geomètrics i estadístics per al modelatge de l'entorn i del propi robot, per a la planificació de tasques i moviments, i per a l'aprenentatge.
2. Aprofundir en l'aprenentatge per reforçament i en l'aprenentatge per demostració, en particular el "mestratge", com a base per a la interacció entre robots, humans i l'entorn.

Cinemàtica i Disseny de Robots:
3. Trobar mètodes generals i complets per a l'anàlisi i la planificació de moviments lliures de col·lisió de mecanismes.
4. Desenvolupar noves estructures mecàniques, preferentment robots paral·lels i robots basats en estructures "tensegrity".
5. Incrementar i millorar l'expertesa del grup en l'àrea del disseny mecànic


La investigación se articula en dos líneas con los objectivos que se detallan a continuación.

Percepción y Manipulación:
1. Enlazar percepción y acción utilitzando métodos geométricos y estadísticos para el modelado del entorno y del propio robot, para la planificación de tareas y movimientos, y para el aprendizaje.
2. Profundizar en el aprendizaje por refuerzo y en el aprendizaje por demostración, en particular el entrenamiento, como base para la interacción entre robots, humanos y el entorno.

Cinemática y Diseño de Robots:
3. Encontrar métodos generales y completos para análisis y planificación de movimientos libres de colisión.
4. Desarrollar nuevas estructuras mecánicas, preferentmente robots paralelos y robots "tensegrity".
5. Incrementar y mejorar la competencia del grupo en el área del diseño mecánico.


Research is organized in two lines with the following goals.

Perception and Manipulation:
1. Linking perception and action using geometric and statistic methods for modelling the environment and the robot, for task and motion planning, and for learning.
2. Deepening on reinforcement learning and in learning by demonstration, in particular "coaching", as a basis for the interaction of robots, humans and the environtment.

Kinematics and Robot Design:
3. Finding general and complete methods for the analysis of mechanisms and for planning collision-free motions.
4. Developing new mechanical structures, especially parallel robots and robots based on tensegrity structures.
5. Increasing and enhancing the expertise of the group in the area of mechanical design.


Research is organized in two lines with the following goals.

Perception and Manipulation:
1. Linking perception and action using geometric and statistic methods for modelling the environment and the robot, for task and motion planning, and for learning.
2. Deepening on reinforcement learning and in learning by demonstration, in particular "coaching", as a basis for the interaction of robots, humans and the environtment.

Kinematics and Robot Design:
3. Finding general and complete methods for the analysis of mechanisms and for planning collision-free motions.
4. Developing new mechanical structures, especially parallel robots and robots based on tensegrity structures.
5. Increasing and enhancing the expertise of the group in the area of mechanical design.

Recent Submissions

  • Perception of cloth in assistive robotic manipulation tasks 

    Jimenez Schlegl, Pablo; Torras, Carme (2020-01-01)
    Article
    Open Access
    Assistive robots need to be able to perform a large number of tasks that imply some type of cloth manipulation. These tasks include domestic chores such as laundry handling or bed-making, among others, as well as dressing ...
  • Contextual policy search for micro-data robot motion learning through covariate Gaussian process latent variable models 

    Delgado Guerrero, Juan Antonio; Colomé Figueras, Adrià; Torras, Carme (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    Conference report
    Open Access
    In the next few years, the amount and variety of context-aware robotic manipulator applications is expected to increase significantly, especially in household environments. In such spaces, thanks to programming by ...
  • Leveraging multiple environments for learning and decision making: a dismantling use case 

    Suárez Hernández, Alejandro; Gaugry, Thierry; Segovia Aguas, Javier; Bernardin, Antonin; Torras, Carme; Marchal, Maud; Alenyà Ribas, Guillem (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    Conference report
    Restricted access - publisher's policy
    Learning is usually performed by observing real robot executions. Physics-based simulators are a good alternative for providing highly valuable information while avoiding costly and potentially destructive robot executions. ...
  • Variable impedance control in cartesian latent space while avoiding obstacles in null space 

    Parent Alonso, David; Colomé Figueras, Adrià; Torras, Carme (2020)
    Conference report
    Open Access
    Human-robot interaction is one of the keys of assistive robots. Robots are expected to be compliant with people but at the same time correctly perform the tasks. In such applications, Cartesian impedance control is preferred ...
  • Interaction identification through tactile sensing during cloth manipulation using a 3-axis touch sensor 

    Geer Couste, Idril-tadzio; Maceira Duch, Marc; Borràs Sol, Júlia; Torras, Carme; Alenyà Ribas, Guillem (2020)
    Conference report
    Open Access
    Tactile feedback during cloth manipulation could be crucial in addressing the huge challenges involved in closing the loop during execution, complementing vision. However, up to our knowledge, tactile sensing has only been ...
  • 3D human shape and pose from a single low-resolution image with self-supervised learning 

    Xu, Xiangyu; Chen, Hao; Moreno-Noguer, Francesc; Jeni, Lázló; De La Torre, Fernando (2020)
    Conference report
    Open Access
    3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating ...
  • Differentiable data augmentation with Kornia 

    Shi, Jian; Riba Pi, Edgar; Mishkin, Dmytro; Moreno-Noguer, Francesc; Nicolaou, Anguelos (2020)
    Conference report
    Open Access
    In this paper we present a review of the Kornia differentiable data augmentation (DDA) module for both for spatial (2D) and volumetric (3D) tensors. This module leverages differentiable computer vision solutions from Kornia, ...
  • C-Flow: conditional generative flow models for images and 3D point clouds 

    Pumarola Peris, Albert; Popov, Stefan; Moreno-Noguer, Francesc; Ferrari, Vittorio (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    Conference report
    Open Access
    Flow-based generative models have highly desirable properties like exact log-likelihood evaluation and exact latent-variable inference, however they are still in their infancy and have not received as much attention as ...
  • Sample-efficient robot motion learning using Gaussian process latent variable models 

    Delgado Guerrero, Juan Antonio; Colomé Figueras, Adrià; Torras, Carme (2020)
    Conference report
    Open Access
    Robotic manipulators are reaching a state where we could see them in household environments in the following decade. Nevertheless, such robots need to be easy to instruct by lay people. This is why kinesthetic teaching has ...
  • Discovering SOCIABLE: using a conceptual model to evaluate the legibility and effectiveness of backchannel cues in an entertainment scenario 

    Andriella, Antonio; Huertas García, Ruben; Forgas Coll, Santiago; Torras, Carme; Alenyà Ribas, Guillem (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    Conference report
    Open Access
    Robots are expected to become part of everyday life. However, while there have been important breakthroughs during the recent decades in terms of technological advances, the ability of robots to interact with humans ...
  • Segmentation and 3D Reconstruction of NON-RIGID Shape from RGB Video 

    Agudo Martínez, Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    Conference report
    Open Access
    In this paper we propose a unsupervised and unified approach to simultaneously recover time-varying 3D shape, camera motion, and temporal clustering into deformations, all of them, from partial 2D point tracks in a RGB ...
  • Neural dense non-rigid structure from motion with latent space constraints 

    Sidhu, Vikramjit; Tretschk, Edgar; Golyanik, Vladislav; Agudo Martínez, Antonio; Theobalt, Christian (2020)
    Conference report
    Open Access
    We introduce the first dense neural non-rigid structure from motion (N-NRSfM) approach, which can be trained end-to-end in an unsupervised manner from 2D point tracks. Compared to the competing methods, our combination of ...

View more